Feature/feat1017 (#2872)

### What problem does this PR solve?

1. fix: mid map show error in knowledge graph, juse because
```@antv/g6```version changed
2. feat: concurrent threads configuration support in graph extractor
3. fix: used tokens update failed for tenant
4. feat: timeout configuration support for llm
5. fix: regex error in graph extractor
6. feat: qwen rerank(```gte-rerank```) support
7. fix: timeout deal in knowledge graph index process. Now chat by
stream output, also, it is configuratable.
8. feat: ```qwen-long``` model configuration

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] New Feature (non-breaking change which adds functionality)

---------

Co-authored-by: chongchuanbing <chongchuanbing@gmail.com>
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>

graphrag/graph_extractor.py

@@ -164,6 +164,7 @@ class GraphExtractor:
         text = perform_variable_replacements(self._extraction_prompt, variables=variables)
         gen_conf = {"temperature": 0.3}
         response = self._llm.chat(text, [{"role": "user", "content": "Output:"}], gen_conf)
+        if response.find("**ERROR**") >= 0: raise Exception(response)
         token_count = num_tokens_from_string(text + response)
 
         results = response or ""

graphrag/index.py

@@ -13,6 +13,7 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 #
+import os
 from concurrent.futures import ThreadPoolExecutor
 import json
 from functools import reduce
@@ -64,7 +65,8 @@ def build_knowledge_graph_chunks(tenant_id: str, chunks: List[str], callback, en
     texts, graphs = [], []
     cnt = 0
     threads = []
-    exe = ThreadPoolExecutor(max_workers=50)
+    max_workers = int(os.environ.get('GRAPH_EXTRACTOR_MAX_WORKERS', 50))
+    exe = ThreadPoolExecutor(max_workers=max_workers)
     for i in range(len(chunks)):
         tkn_cnt = num_tokens_from_string(chunks[i])
         if cnt+tkn_cnt >= left_token_count and texts:

graphrag/mind_map_extractor.py

@@ -16,6 +16,7 @@
 
 import collections
 import logging
+import os
 import re
 import logging
 import traceback
@@ -89,7 +90,8 @@ class MindMapExtractor:
             prompt_variables = {}
 
         try:
-            exe = ThreadPoolExecutor(max_workers=12)
+            max_workers = int(os.environ.get('MINDMAP_EXTRACTOR_MAX_WORKERS', 12))
+            exe = ThreadPoolExecutor(max_workers=max_workers)
             threads = []
             token_count = max(self._llm.max_length * 0.8, self._llm.max_length-512)
             texts = []